AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

[Re] End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking

Sean McLeish, Long Tran-Thanh

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Neural-symbolic reasoning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add recall to the recurrent network (ablation)Deep Thinking networks · 512-bit prefix sumsaccuracy: $0.00 \pm 0.00$ -> $96.19 \pm 3.73$Improved
Add progressive loss to DT-Recall (ablation)DT-Recall · 512-bit prefix sumsaccuracy: $96.19 \pm 3.73$ -> $97.12 \pm 1.88$Improved
Use progressive loss without recall (ablation)Deep Thinking network · 512-bit prefix sumsaccuracy: $0.00 \pm 0.00$ -> $11.26 \pm 6.90$Improved
Sample n randomly rather than fixing n=0 (ablation)DT-Recall · 512-bit prefix sumsaccuracy: $90.27 \pm 5.95\%$ -> $97.12 \pm 1.88\%$Improved
Add recall to the recurrent network (ablation)Deep Thinking networks · 59 × 59 mazesaccuracy: $0.00 \pm 0.00$ -> $82.72 \pm 15.14$Improved
Add progressive loss to DT-Recall (ablation)DT-Recall · 59 × 59 mazesaccuracy: $82.72 \pm 15.14$ -> $97.30 \pm 0.68$Improved
Add recall to the recurrent network (ablation)Deep Thinking networks · 13 × 13 mazesaccuracy: $85.59 \pm 2.81$ -> $99.94 \pm 0.03$Improved
Add recall to the recurrent network (ablation)Deep Thinking networks · Chess puzzles 600K–700Kaccuracy: $78.81 \pm 1.04$ -> $82.12 \pm 0.69$Improved
Add progressive loss to DT-Recall (ablation)DT-Recall · Chess puzzles 600K–700Kaccuracy: $82.12 \pm 0.69$ -> $82.69 \pm 0.27$Improved
Use a runtime-penalty loss (ablation)Deep Thinking network · 512-bit prefix sumsaccuracy: $72.45 \pm 8.91\%$Hurt
Use a runtime-penalty loss (ablation)Deep Thinking network · 59 × 59 mazesaccuracy: 0%Hurt
Add progressive loss to DT-Recall (ablation)DT-Recall · Chess puzzles 600K–700Kaccuracy: 83% -> 97%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy